Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to actions or processes involving change, rebuilding, and connections between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .rdf
    -0.15
    éĽ²
    -0.15
     Dai
    -0.15
    vars
    -0.15
    izard
    -0.14
     Horny
    -0.14
    /plain
    -0.14
    Plain
    -0.14
     ;č↵
    -0.14
    ivant
    -0.14
    POSITIVE LOGITS
    igate
    0.15
     Heath
    0.15
    çij
    0.14
    utral
    0.14
    åĨħéĥ¨
    0.13
    ä½Ļ
    0.13
    åĭĻ
    0.13
    polator
    0.13
    oyer
    0.13
    ween
    0.13
    Act Density 0.004%

    No Known Activations